mirror of
https://gitlab.freedesktop.org/gstreamer/gstreamer.git
synced 2024-12-04 23:46:43 +00:00
8afc305fe2
- Propagate GstTensor.type becoming to GstTensor.data_type to tensor producer (onnx) and consumer (TensorDecoder) Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6061> |
||
---|---|---|
.. | ||
decoders | ||
tensor | ||
gstml.h | ||
gstonnx.c | ||
gstonnxclient.cpp | ||
gstonnxclient.h | ||
gstonnxinference.cpp | ||
gstonnxinference.h | ||
meson.build | ||
README.md |
ONNX Build Instructions
Build
- do a recursive checkout of onnxruntime tag 1.16.3
$SRC_DIR
and$BUILD_DIR
are local source and build directories- To run with CUDA, both CUDA and cuDNN libraries must be installed.
$ cd $SRC_DIR
$ git clone --recursive https://github.com/microsoft/onnxruntime.git && cd onnxruntime && git checkout -b v1.16.3 refs/tags/v1.16.3
$ mkdir $BUILD_DIR/onnxruntime && cd $BUILD_DIR/onnxruntime
- CPU
$ cmake -Donnxruntime_BUILD_SHARED_LIB=ON -DBUILD_TESTING=OFF -Donnxruntime_BUILD_UNIT_TESTS=OFF $SRC_DIR/onnxruntime/cmake && make -j$(nproc) && sudo make install
- CUDA
cmake -Donnxruntime_BUILD_SHARED_LIB=ON -DBUILD_TESTING=OFF -Donnxruntime_BUILD_UNIT_TESTS=OFF -Donnxruntime_USE_CUDA=ON -Donnxruntime_CUDA_HOME=/usr/local/cuda -Donnxruntime_CUDNN_HOME=/usr/local/cuda -DCMAKE_CUDA_ARCHITECTURES=native -DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc $SRC_DIR/onnxruntime/cmake && make -j$(nproc) && sudo make install
- Intel oneDNN
3.0 install intel oneDNN
3.1 clone, build and install Khronos OpenCL SDK. Build dependencies for Fedora are
sudo dnf install libudev-devel libXrandr-devel mesa-libGLU-devel mesa-libGL-devel libX11-devel intel-opencl
3.2 build and install onnxruntime
:
cmake -Donnxruntime_BUILD_SHARED_LIB=ON -DBUILD_TESTING=OFF -Donnxruntime_BUILD_UNIT_TESTS=OFF -Donnxruntime_USE_DNNL=ON -Donnxruntime_DNNL_GPU_RUNTIME=ocl -Donnxruntime_DNNL_OPENCL_ROOT=$SRC_DIR/OpenCL-SDK/install $SRC_DIR/onnxruntime/cmake && make -j$(nproc) && sudo make install